Skip to content

VolsungaSaga/f1tenth_sim

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Using Reinforcement Learning to Drive an Autonomous Car
----------------------------------------------------------

Instructions for Setup/Use

In order to use this package, you will need a couple of packages.

ROS Dependencies:
- ROS Kinetic Kame
- ros-control
- gazebo7
Other Dependencies:
- TensorFlow
- NumPy
- SciPy
- Stable-Baselines (a fork of OpenAI)

ROS Kinetic uses Python2.7, while TensorFlow and Stable-Baselines use Python3. If you attempt to run the training script without using virtual environments to isolate each Python version and their libraries, you won't succeed.

Essentially, you want to create two environments (I recommend using virtualenv for creating them). The system environment (or the 1st virtual environment) should have Python2.7 and ROS Kinetic installed, while the 2nd virtual environment should have Python3 and stable-baselines installed. If you use pip to install stable-baselines, it should install all the dependencies along with it.

About

This is the repository for my degree project, "Using Reinforcement Learning to Train an Autonomous Car". It includes an OpenAI-Gazebo interface, plus a training script.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages

  • Python 95.1%
  • CMake 4.7%
  • Shell 0.2%